Abstract

We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI--SVM in terms of latent variables. A latent SVM is semiconvex, and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function.

Keywords

Pascal (unit)Artificial intelligenceComputer scienceLatent variableSupport vector machineDiscriminative modelPattern recognition (psychology)Object detectionLatent variable modelMachine learningProbabilistic latent semantic analysisTraining setMargin (machine learning)

Affiliated Institutions

Related Publications

Publication Info

Year
2009
Type
article
Volume
32
Issue
9
Pages
1627-1645
Citations
9911
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

9911
OpenAlex

Cite This

Pedro F. Felzenszwalb, Ross Girshick, David McAllester et al. (2009). Object Detection with Discriminatively Trained Part-Based Models. IEEE Transactions on Pattern Analysis and Machine Intelligence , 32 (9) , 1627-1645. https://doi.org/10.1109/tpami.2009.167

Identifiers

DOI
10.1109/tpami.2009.167